At the start of building a request, we would wait for roughly enough
space to fit the average request (to reduce the likelihood of having to
wait and abort partway through request construction). To achieve we
would try to begin a 0-length command packet, this just adds extra
confusion so make the wait-for-space explicit, as in the next patch we
want to move it from the backend to the i915_gem_request_alloc() so it
can ensure that the wait-for-space is the first operation in building a
new request.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171115151204.8105-2-chris@chris-wilson.co.uk
Take a copy of the HW state after a reset upon module loading by
executing a context switch from a blank context to the kernel context,
thus saving the default hw state over the blank context image.
We can then use the default hw state to initialise any future context,
ensuring that each starts with the default view of hw state.
v2: Unmap our default state from the GTT after stealing it from the
context. This should stop us from accidentally overwriting it via the
GTT (and frees up some precious GTT space).
Testcase: igt/gem_ctx_isolation
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171110142634.10551-7-chris@chris-wilson.co.uk
In the next few patches, we will want to both copy out of the context
image and write a valid image into a new context. To be completely safe,
we should then couple in our domain tracking to ensure that we don't
have any issues with stale data remaining in unwanted cachelines.
Historically, we omitted the .write=true from the call to set-gtt-domain
in i915_switch_context() in order to avoid a stall between every request
as we would want to wait for the previous context write from the gpu.
Since then, we limit the set-gtt-domain to only occur when we first bind
the vma, so once in use we will never stall, and we are sure to flush
the context following a load from swap.
Equally we never applied the lessons learnt from ringbuffer submission
to execlists; so time to apply the flush of the lrc after load as well.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171110142634.10551-6-chris@chris-wilson.co.uk
Trying to enable printk debugging for GEM is fraught with the issue of
spam; interactions with HW are very frequent and often boring. However,
one instance where they are not so boring is just before a BUG; here
ftrace provides a facility to dump its ringbuffer on an oops. So for CI
let's enable trace_printk() to capture the last exchanges with HW as a
death rattle.
For example,
[ 79.234110] ------------[ cut here ]------------
[ 79.234137] kernel BUG at drivers/gpu/drm/i915/intel_lrc.c:907!
[ 79.234145] invalid opcode: 0000 [#1] SMP
[ 79.234153] Dumping ftrace buffer:
[ 79.234158] ---------------------------------
...
[ 79.314044] gem_conc-1059 1..s1 79203443us : intel_lrc_irq_handler: bcs0 out[0]: ctx=5.2, seqno=145
[ 79.314089] gem_conc-1059 1..s. 79220800us : intel_lrc_irq_handler: bcs0 csb[1/1]: status=0x00000018:0x00000005
[ 79.314133] gem_conc-1059 1..s. 79220803us : intel_lrc_irq_handler: bcs0 out[0]: ctx=5.1, seqno=145
[ 79.314177] gem_conc-1062 2..s1 79230458us : intel_lrc_irq_handler: bcs0 in[0]: ctx=8.1, seqno=146
[ 79.314220] gem_conc-1062 2..s1 79230515us : intel_lrc_irq_handler: bcs0 in[0]: ctx=8.2, seqno=147
[ 79.314265] gem_conc-1059 1..s1 79230951us : intel_lrc_irq_handler: bcs0 csb[2/3]: status=0x00000012:0x00000008
[ 79.314309] gem_conc-1059 1..s1 79230954us : intel_lrc_irq_handler: bcs0 out[0]: ctx=8.2, seqno=147
[ 79.314353] gem_conc-1059 1..s1 79230954us : intel_lrc_irq_handler: bcs0 csb[3/3]: status=0x00008002:0x00000008
[ 79.314396] gem_conc-1059 1..s1 79230955us : intel_lrc_irq_handler: bcs0 out[0]: ctx=8.1, seqno=147
[ 79.314402] ---------------------------------
v2: Tweak the formatting to be more consistent between in/out.
v3: do {} while (0) stub macro protection
Suggested-by: Michał Winiarski <michal.winiarski@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171109143019.16568-1-chris@chris-wilson.co.uk
Pretty similar to what we have on execlists.
We're reusing most of the GEM code, however, due to GuC quirks we need a
couple of extra bits.
Preemption is implemented as GuC action, and actions can be pretty slow.
Because of that, we're using a mutex to serialize them. Since we're
requesting preemption from the tasklet, the task of creating a workitem
and wrapping it in GuC action is delegated to a worker.
To distinguish that preemption has finished, we're using additional
piece of HWSP, and since we're not getting context switch interrupts,
we're also adding a user interrupt.
The fact that our special preempt context has completed unfortunately
doesn't mean that we're ready to submit new work. We also need to wait
for GuC to finish its own processing.
v2: Don't compile out the wait for GuC, handle workqueue flush on reset,
no need for ordered workqueue, put on a reviewer hat when looking at my own
patches (Chris)
Move struct work around in intel_guc, move user interruput outside of
conditional (Michał)
Keep ring around rather than chase though intel_context
v3: Extract WA for flushing ggtt writes to a helper (Chris)
Keep work_struct in intel_guc rather than engine (Michał)
Use ordered workqueue for inject_preempt worker to avoid GuC quirks.
v4: Drop now unused INTEL_GUC_PREEMPT_OPTION_IMMEDIATE (Daniele)
Drop stray newlines, use container_of for intel_guc in worker,
check for presence of workqueue when flushing it, rather than
enable_guc_submission modparam, reorder preempt postprocessing (Chris)
v5: Make wq NULL after destroying it
v6: Swap struct guc_preempt_work members (Michał)
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171026133558.19580-1-michal.winiarski@intel.com
Originally we set the priority to max upon inserting the request into
the execlists queue (and removing it from the scheduler lists). We could
then use the prio==INT_MAX as a shortcut within execlists_schedule() to
detect the end of the dependency chain. Since commit 1f181225f8
("drm/i915/execlists: Keep request->priority for its lifetime") this is
no longer true as we use the request completion as an indicator the
schedule dependency chain is complete instead. (This allows us to then
reschedule requests even when its context is in flight.) However, this
makes the GEM_BUG_ON() inside execlists_schedule() racy as we may change
the rq->prio at the same time. As the assertion is useful, let's keep
the assertion and remove the micro-optimisation.
Fixes: 1f181225f8 ("drm/i915/execlists: Keep request->priority for its lifetime")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024115501.21033-1-chris@chris-wilson.co.uk
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Back in commit a4b2b01523 ("drm/i915: Don't mark an execlists
context-switch when idle") we noticed the presence of late
context-switch interrupts. We were able to filter those out by looking
at whether the ELSP remained active, but in commit beecec9017
("drm/i915/execlists: Preemption!") that became problematic as we now
anticipate receiving a context-switch event for preemption while ELSP
may be empty. To restore the spurious interrupt suppression, add a
counter for the expected number of pending context-switches and skip if
we do not need to handle this interrupt to make forward progress.
v2: Don't forget to switch on for preempt.
v3: Reduce the counter to a on/off boolean tracker. Declare the HW as
active when we first submit, and idle after the final completion event
(with which we confirm the HW says it is idle), and track each source
of activity separately. With a finite number of sources, it should aide
us in debugging which gets stuck.
Fixes: beecec9017 ("drm/i915/execlists: Preemption!")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Arkadiusz Hiler <arkadiusz.hiler@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171023213237.26536-3-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
In the next patch, we want to reduce the lock coverage within the
shrinker, and one of the dangerous walks we have is over obj->vma_list.
We are only walking the obj->vma_list in order to check whether it has
been permanently pinned by HW access, typically via use on the scanout.
But we have a couple of other long term pins, the context objects for
which we currently have to check the individual vma pin_count. If we
instead mark these using obj->pin_display, we can forgo the dangerous
and sometimes slow list iteration.
v2: Rearrange code to try and avoid confusion from false associations
due to arrangement of whitespace along with rebasing on obj->pin_global.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171013202621.7276-4-chris@chris-wilson.co.uk
When we write to ELSP, it triggers a context preemption at the earliest
arbitration point (3DPRIMITIVE, some PIPECONTROLs, a few other
operations and the explicit MI_ARB_CHECK). If this is to the same
context, it triggers a LITE_RESTORE where the RING_TAIL is merely
updated (used currently to chain requests from the same context
together, avoiding bubbles). However, if it is to a different context, a
full context-switch is performed and it will start to execute the new
context saving the image of the old for later execution.
Previously we avoided preemption by only submitting a new context when
the old was idle. But now we wish embrace it, and if the new request has
a higher priority than the currently executing request, we write to the
ELSP regardless, thus triggering preemption, but we tell the GPU to
switch to our special preemption context (not the target). In the
context-switch interrupt handler, we know that the previous contexts
have finished execution and so can unwind all the incomplete requests
and compute the new highest priority request to execute.
It would be feasible to avoid the switch-to-idle intermediate by
programming the ELSP with the target context. The difficulty is in
tracking which request that should be whilst maintaining the dependency
change, the error comes in with coalesced requests. As we only track the
most recent request and its priority, we may run into the issue of being
tricked in preempting a high priority request that was followed by a
low priority request from the same context (e.g. for PI); worse still
that earlier request may be our own dependency and the order then broken
by preemption. By injecting the switch-to-idle and then recomputing the
priority queue, we avoid the issue with tracking in-flight coalesced
requests. Having tried the preempt-to-busy approach, and failed to find
a way around the coalesced priority issue, Michal's original proposal to
inject an idle context (based on handling GuC preemption) succeeds.
The current heuristic for deciding when to preempt are only if the new
request is of higher priority, and has the privileged priority of
greater than 0. Note that the scheduler remains unfair!
v2: Disable for gen8 (bdw/bsw) as we need additional w/a for GPGPU.
Since, the feature is now conditional and not always available when we
have a scheduler, make it known via the HAS_SCHEDULER GETPARAM (now a
capability mask).
v3: Stylistic tweaks.
v4: Appease Joonas with a snippet of kerneldoc, only to fuel to fire of
the preempt vs preempting debate.
Suggested-by: Michal Winiarski <michal.winiarski@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Arkadiusz Hiler <arkadiusz.hiler@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Ben Widawsky <benjamin.widawsky@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171003203453.15692-8-chris@chris-wilson.co.uk
With preemption, we will want to "unsubmit" a request, taking it back
from the hw and returning it to the priority sorted execution list. In
order to know where to insert it into that list, we need to remember
its adjust priority (which may change even as it was being executed).
This also affects reset for execlists as we are now unsubmitting the
requests following the reset (rather than directly writing the ELSP for
the inflight contexts). This turns reset into an accidental preemption
point, as after the reset we may choose a different pair of contexts to
submit to hw.
GuC is not updated as this series doesn't add preemption to the GuC
submission, and so it can keep benefiting from the early pruning of the
DFS inside execlists_schedule() for a little longer. We also need to
find a way of reducing the cost of that DFS...
v2: Include priority in error-state
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171003203453.15692-6-chris@chris-wilson.co.uk
Given the mechanism to unwind and replay requests (designed to support
preemption), we have an alternative to the current method of
resubmitting the ELSP upon reset. Resubmitting ELSP turns out to be more
complicated than expected, due to having to handle lost context-switch
interrupts and so guessing what ELSP we need to resubmit later. Instead,
by unwinding the requests and clearing the ELSP tracking entirely, we
can then just dequeue the first pair of ready requests after resetting,
using the normal submission procedure.
Currently, the unwound requests have maximum priority and so are
guaranteed to be resubmitted upon resume. If we are lucky, we may be
able to coalesce a new request on top!
Suggested-by: Michał Winiarski <michal.winiarski@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170916204414.32762-4-chris@chris-wilson.co.uk
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
During a reset, we may skip over completed requests and lost
context-switch interrupts. Following the reset, we may then may end up
with no active requests in the ELSP (and so do not resubmit to restart
the engine), but have a queue of requests ready for execution. This is
unlikely, it requires the last request to complete after the hang is
detected, but not impossible. The outcome of this is that the engine
stalls, possibly leading to full ring and indefinite wait under
struct_mutex, eventually leading to a full driver hang.
Alternatively, we can solve this by unsubmitting the incomplete requests
and just kickstarting the tasklet. Michał has patches for that, which I
initially disliked due to the extra complexity, but the complexity of
this "simple" restart is growing...
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170916204414.32762-1-chris@chris-wilson.co.uk
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
The engine also provides a mirror of the CSB write pointer in the HWSP,
but not of our read pointer. To take advantage of this we need to
remember where we read up to on the last interrupt and continue off from
there. This poses a problem following a reset, as we don't know where
the hw will start writing from, and due to the use of power contexts we
cannot perform that query during the reset itself. So we continue the
current modus operandi of delaying the first read of the context-status
read/write pointers until after the first interrupt. With this we should
now have eliminated all uncached mmio reads in handling the
context-status interrupt, though we still have the uncached mmio writes
for submitting new work, and many uncached mmio reads in the global
interrupt handler itself. Still a step in the right direction towards
reducing our resubmit latency, although it appears lost in the noise!
v2: Cannonlake moved the CSB write index
v3: Include the sw/hwsp state in debugfs/i915_engine_info
v4: Also revert to using CSB mmio for GVT-g
v5: Prevent the compiler reloading tail (Mika)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Acked-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913085605.18299-6-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
The engine provides a mirror of the CSB in the HWSP. If we use the
cacheable reads from the HWSP, we can shave off a few mmio reads per
context-switch interrupt (which are quite frequent!). Just removing a
couple of mmio is not enough to actually reduce any latency, but a small
reduction in overall cpu usage.
Much appreciation for Ben dropping the bombshell that the CSB was in the
HWSP and for Michel in digging out the details.
v2: Don't be lazy, add the defines for the indices.
v3: Include the HWSP in debugfs/i915_engine_info
v4: Check for GVT-g, it currently depends on intercepting CSB mmio
v5: Fixup GVT-g mmio path
v6: Disable HWSP if VT-d is active as the iommu adds unpredictable
memory latency. (Mika)
v7: Also markup the CSB read with READ_ONCE() as it may still be an mmio
read and we want to stop the compiler from issuing a later (v.slow) reload.
Suggested-by: Ben Widawsky <benjamin.widawsky@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Acked-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913133534.26927-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
The context descriptor is stored inside the per-engine context state, as
we only need to compute it once and access it frequently. However,
currently only intel_lrc.c has easy access, but i915_guc_submission.c
would like to frequently read it as well, and more so only ever needs
the lower 32bits. Make it an inline as the compiler should be able to
retrieve the value in less instructions than it takes to do the function
call:
add/remove: 0/1 grow/shrink: 1/0 up/down: 8/-45 (-37)
function old new delta
i915_guc_submit 621 629 +8
intel_lr_context_descriptor 45 - -45
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170912214905.21987-1-chris@chris-wilson.co.uk
Reviewed-by: Oscar Mateo <oscar.mateo@intel.com>
Let's inherit workarounds from previous platforms that
according to wa_database and BSpec are still valid for
Cannonlake.
v2: Add missed workarounds.
v3: Rebase
v4: Remove bad chunk that was added to rc6 disable. (Ander)
Also remove A0 W/a that are not needed anymore.
v5: Rebase on top of CFL.
v6: Remove empty gen9_init_perctx_bb and gen9_init_indirectctx_bb
since they don't carry any gen10 related W/a. (by Oscar).
Also Remove A0 exclusive workaround.
v7: Remove more A0 exclusive workarounds. As pointed out by Oscar
many workarounds were changed to be A0 only so let's remove
them.
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Oscar Mateo <oscar.mateo@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170815231651.975-1-rodrigo.vivi@intel.com
